Nettskjema MCP Server
Enables interaction with Nettskjema forms, submissions, invitations, and data export through the MCP protocol.
README
Nettskjema MCP Server
Model Context Protocol (MCP) server for the Nettskjema API. This server provides tools to interact with Nettskjema forms, submissions, invitations, and more through the MCP protocol.
Features
- OAuth 2.1 Authentication: Secure client credentials flow with 24-hour token caching
- Form Management: List, retrieve, and update forms
- Submissions: Access and manage form submissions
- Invitations: Create and manage form invitations
- Data Export: Export form responses as CSV, Excel, and SPSS
- User Information: Get authenticated user details
- Automatic Token Management: Tokens are cached and automatically refreshed
Installation
- Clone this repository:
git clone <repository-url>
cd nettskjema-mcp
- Install dependencies using pip:
pip install -e .
Or using uv:
uv pip install -e .
Configuration
1. Create API Client Credentials
- Log into https://authorization.nettskjema.no/
- Click "Register client"
- Provide a client name and email
- Save the clientSecret immediately - it's shown only once!
- Note your
clientIdandclientSecret
2. Configure Environment Variables
Create a .env file from the example:
cp .env.example .env
Add your credentials to the .env file:
NETTSKJEMA_CLIENT_ID=your_client_id_here
NETTSKJEMA_CLIENT_SECRET=your_client_secret_here
Security Note: Never commit or hardcode your clientSecret in code. It's like a password and valid for 365 days. Store it in environment variables or a secure vault.
Token Management: OAuth access tokens are valid for 24 hours and are automatically cached and reused by the server. You don't need to manage token refresh manually.
3. Grant Form Access
Your API client username is: <clientId>@apiclient
For each form you want to access, add this username to the form permissions:
- Open the form in Nettskjema
- Go to: Settings → Permissions → Editing permissions
- Add your client username
Usage
Running the Server
After installation, you can run the server using the installed command:
nettskjema-mcp
Or run as a Python module:
python -m nettskjema_mcp
For development (without installation):
python -m nettskjema_mcp
MCP Client Configuration
Add this to your MCP client configuration (e.g., Claude Desktop config):
Option 1: Using installed command (recommended)
{
"mcpServers": {
"nettskjema": {
"command": "nettskjema-mcp",
"env": {
"NETTSKJEMA_CLIENT_ID": "your_client_id_here",
"NETTSKJEMA_CLIENT_SECRET": "your_client_secret_here"
}
}
}
}
Option 2: Using Python module (for development)
{
"mcpServers": {
"nettskjema": {
"command": "python",
"args": ["-m", "nettskjema_mcp"],
"cwd": "/path/to/nettskjema-mcp",
"env": {
"NETTSKJEMA_CLIENT_ID": "your_client_id_here",
"NETTSKJEMA_CLIENT_SECRET": "your_client_secret_here"
}
}
}
}
Available Tools
Authentication & User
check_auth_status- Check OAuth authentication status and token info (debugging)get_user_info- Get authenticated user information
Forms
list_my_forms- List all your formscreate_form- Create a new formdelete_forms- Delete forms with trash retentionget_form_info- Get metadata for a specific formget_form_settings- Get form configurationget_form_elements- Get all questions/elements in a formget_form_definition- Get complete form definitionupdate_form_settings- Update form settingslookup_form_by_title- Find form ID by short title
Submissions
submit_form- Submit a response to a formget_submission- Get a single submission with answersget_submission_metadata- Get metadata for all submissionslist_my_submissions- List your submissionsget_form_answers- Get all answers for a formdelete_submissions- Delete specific submissions
Data Export
export_form_csv- Export responses as CSVexport_form_excel- Export responses as Excelget_spss_syntax- Generate SPSS syntax file
Invitations
get_invitations- List all form invitationscreate_invitation- Create new invitation with optional SMSdelete_invitations- Delete specific invitationssend_reminder- Send reminder notifications
Quick Start
After installation and configuration, you can use the MCP server with any MCP-compatible client. Here are some example use cases:
List Your Forms
Use the list_my_forms tool to see all forms you have access to.
Get Form Details
Use get_form_info with a form_id to see the form's metadata.
Use get_form_elements to see all questions in the form.
Export Data
Use export_form_csv or export_form_excel to download form responses.
Use get_form_answers to get raw answer data.
Manage Invitations
Use create_invitation to invite someone to fill out a form.
Use send_reminder to remind people who haven't responded yet.
API Documentation
Full Nettskjema API documentation: https://nettskjema.no/apidoc
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.